Die Werkzeugbeschreibungen sind auf Englisch.

Technologieradare: Agents, skills and MCP

Radarfilter

Werkzeug-Rangliste

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1

    Agent
    Aktiv

    Build production marketing sites with Claude Code — an Astro + Cloudflare Workers template, a WordPress→Astro migration playbook, and 36 silent failures documented from real rebuilds.

    JavaScriptLizenz: MIT
    • ai-agents
    • astro
    • claude-code
    • claude-code-skill
    • cloudflare-workers

    githubgemessenes WachstumQuelle öffnen ↗

    22GitHub-Sterne+11 (+100.0 %)
  2. 2

    Agent
    Aktiv

    Serve any ACP coding agent — Claude Code, Gemini CLI, Codex — over the A2A protocol, with tool progress, file diffs, and permission prompts preserved.

    PythonLizenz: Apache-2.0
    • a2a
    • agent-protocol
    • agent2agent
    • ai-agents
    • anthropic

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+2 (+100.0 %)
  3. 3

    Agent
    Aktiv

    The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.

    PythonLizenz: Apache-2.0
    • a2a
    • agent
    • agent-framework
    • ai-agent
    • artificial-intelligence

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+2 (+200.0 %)
  4. 4

    Agent
    Aktiv

    Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server

    PythonLizenz: MIT
    • a2a
    • agents
    • ai-agents
    • claude
    • claude-code

    githubgemessenes WachstumQuelle öffnen ↗

    8GitHub-Sterne+3 (+60.0 %)
  5. 5

    Agent
    Aktiv

    OpenSpawn — An open source multi-agent coordination platform

    TypeScriptLizenz: MIT
    • a2a
    • agent-coordination
    • agent-framework
    • agent-orchestration
    • ai-agents

    githubgemessenes WachstumQuelle öffnen ↗

    9GitHub-Sterne+3 (+50.0 %)
  6. 6

    Agent
    Aktiv

    Agent control plane and runtime access platform for enterprise systems — govern business APIs as Tools, compose Agents and Workflows, expose runtimes through AAP, and trace executions end to end. https://act-weave.grok.me

    GoLizenz: Apache-2.0
    • a2a
    • a2ui
    • agent
    • agent-control-plane
    • agent-runtime

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sterne+1 (+100.0 %)
  7. 7

    Agent
    Ruhend

    Vendor-neutral identity verification for AI agents

    PythonLizenz: Apache-2.0
    • a2a
    • agent-identity
    • ai-agents
    • authentication
    • mcp

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sterne+1 (+100.0 %)
  8. 8

    Agent
    Aktiv

    Autonomous Execution Gateway: before AI agents execute tools, payments, or workflows, InterAI verifies risk, policy, and trust receipts.

    TypeScript
    • a2a
    • agent-safety
    • ai-agents
    • autonomous-agents
    • base-usdc

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sterne+1 (+100.0 %)
  9. 9

    Agent
    Aktiv

    A registry website for hosting the a2a agents that were built using the Inference Gateway ADK

    VueLizenz: Apache-2.0
    • a2a
    • a2a-protocol
    • agents
    • container-as-a-service
    • containers

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sterne+1 (+100.0 %)
  10. 10

    Agent
    Aktiv

    Attenu Guard for TypeScript — per-agent permissions on every tool call and sub-agent handoff (a sub-agent never holds more than its parent) with a hash-chained audit log verified offline; same bundle format as the Python library.

    TypeScriptLizenz: Apache-2.0
    • a2a
    • agent-authorization
    • agent-security
    • agentic-ai
    • ai-agent

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sterne+1
  11. 11

    Agent
    Aktiv

    全栈AI投研Agent · Your AI research co-pilot for smarter investment decisions. Five integrated research frameworks: Serenity industry-chain analysis, Buffett value-investing filter, UZI-Skill 22-dim deep analysis, TradingAgents multi-agent…

    PythonLizenz: MIT
    • ai-agent
    • chinese-stock-market
    • claude-code-skill
    • financial-analysis
    • industry-chain-analysis

    githubgemessenes WachstumQuelle öffnen ↗

    11GitHub-Sterne+3 (+37.5 %)
  12. 12

    Agent
    Aktiv

    Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability.

    PythonLizenz: Apache-2.0
    • a2a-protocol
    • agentcore
    • agentcore-agent
    • agentcore-gateway
    • agentcore-identity

    githubgemessenes WachstumQuelle öffnen ↗

    6GitHub-Sterne+2 (+50.0 %)
  13. 13

    Agent
    Aktiv

    AI Workflows For Kubernetes

    Go
    • a2a
    • ai-agents
    • kagent
    • kubernetes
    • workflows

    githubgemessenes WachstumQuelle öffnen ↗

    12GitHub-Sterne+3 (+33.3 %)
  14. 14

    Agent
    Ruhend

    The identity layer for AI agents: open standard, SDKs, and framework integrations for verifiable agent identity.

    Python
    • a2a
    • agent-did
    • ai-agents
    • crewai
    • decentralized-identity

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+1 (+50.0 %)
  15. 15

    Agent
    Aktiv

    The ultimate A2A agents troubleshooter

    GoLizenz: Apache-2.0
    • a2a
    • agentic-ai
    • debugger
    • utils

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+1 (+50.0 %)
  16. 16

    Agent
    Ruhend

    A local, privacy-first AI agent (Rust) that connects LLMs to your email, calendar, browser, code, and messages — 75+ tools, MCP/A2A support, Discord/Slack/iMessage channels, autonomous agent loop.

    RustLizenz: MIT
    • a2a
    • agent
    • ai
    • ai-agent
    • autonomous-agent

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+1 (+50.0 %)
  17. 17

    Agent
    Aktiv

    Disposable collaboration rooms for AI agents working across machines and tools

    TypeScriptLizenz: Apache-2.0
    • a2a
    • agent-collaboration
    • ai-agents
    • cloudflare-workers
    • codex

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+1 (+33.3 %)
  18. 18

    Agent
    Ruhend

    Connect Slack to your Claude Code agents - Zero API costs, full context retention, custom skills & hooks. Unlike official Claude for Slack, we connect to your RUNNING agents.

    TypeScriptLizenz: MIT
    • ai-agents
    • ai-coding
    • anthropic
    • automation
    • claude

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+1 (+33.3 %)
  19. 19

    Agent
    Aktiv

    한국 취준생 자소서 작성 멀티 에이전트 Claude Code 스킬 심층 인터뷰로 소재 발굴, 경험카드·claim-map으로 날조 차단, 사용자 문체 반영

    PythonLizenz: MIT
    • ai-agents
    • claude-code
    • claude-code-skill
    • cover-letter
    • jasoseo

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+1 (+33.3 %)
  20. 20

    Agent
    Aktiv

    Dispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks

    Lizenz: MIT
    • agentic
    • ai-agents
    • anthropic
    • audit
    • automation

    githubgemessenes WachstumQuelle öffnen ↗

    12GitHub-Sterne+2 (+20.0 %)
  21. 21

    Agent
    Aktiv

    Expose OpenCode through A2A with an inbound server surface and embedded outbound client.

    PythonLizenz: Apache-2.0
    • a2a
    • a2a-agent
    • a2a-client
    • a2a-protocol
    • a2a-server

    githubgemessenes WachstumQuelle öffnen ↗

    25GitHub-Sterne+3 (+13.6 %)
  22. 22

    Agent
    Aktiv

    A Claude skill and standalone CLI for inspecting, debugging, and injecting code into a running Steam client (desktop or Steam Deck) via the Chrome DevTools Protocol (CDP)

    JavaScriptLizenz: CC0-1.0
    • ai-agent
    • claude-code
    • claude-code-skill
    • skill-md

    githubgemessenes WachstumQuelle öffnen ↗

    5GitHub-Sterne+1 (+25.0 %)
  23. 23

    Agent
    Aktiv

    Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests

    Lizenz: MIT
    • ai-agents
    • anthropic
    • automation
    • bugs
    • claude

    githubgemessenes WachstumQuelle öffnen ↗

    5GitHub-Sterne+1 (+25.0 %)
  24. 24

    Agent
    Aktiv

    Utilities to spin up Pydantic AI agents with a few additional enhancements and integrations

    PythonLizenz: MIT
    • a2a
    • agents
    • embeddings
    • mcp
    • pydantic-ai

    githubgemessenes WachstumQuelle öffnen ↗

    5GitHub-Sterne+1 (+25.0 %)

Lern- und Referenzressourcen

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.

  1. 1

    30x-outreach

    Agent
    AktivQuelle öffnen ↗

    Auditable outbound experiments from verified signals to deterministic quality gates, exact-payload approval, safe execution, and compounding learning.

    Python
    • ai-agents
    • claude-code-skill
    • cold-email
    • demand-generation
    • experimentation
    githubRessourcegemessenes Wachstum
    3GitHub-Sterne+1 (+50.0 %)